Unlock instant, AI-driven research and patent intelligence for your innovation.

Facial image super-resolution method based on dictionary asymptotic updating

A face image and super-resolution technology, applied in image enhancement, image data processing, character and pattern recognition, etc., can solve the problems of lack of reliability of reconstruction results, insufficient mining of geometric structure information, etc.

Active Publication Date: 2014-09-10
WUHAN UNIV
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Whether using the least squares representation method, sparse representation method, local constraint representation method or iterative neighborhood embedding method, they all try to maintain the low-resolution manifold structure to the reconstructed high-resolution space, and do not fully explore the The geometric structure information of the original high-resolution manifold space is affected by the degradation process, which makes the reconstruction results unreliable

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Facial image super-resolution method based on dictionary asymptotic updating
  • Facial image super-resolution method based on dictionary asymptotic updating
  • Facial image super-resolution method based on dictionary asymptotic updating

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] An embodiment includes the following sub-steps:

[0087] Step 4.1, set b=0, input the low-resolution face image to be tested Low-resolution dictionary I for all levels L(0) , I L(1) , I L(2) ,...,I L(B) and high-resolution face image training set I H ,

[0088] Step 4.2, according to the b-th layer low-resolution dictionary I L(b) , for the estimated high-resolution face image (b=0, that is, the first execution of step 4.2 adopts the low-resolution face image to be tested As an initial estimated high-resolution face image ) for super-resolution reconstruction to obtain an estimated high-resolution face image

[0089] When step 4.2 is executed for the first time, b=0, the low-resolution dictionary of the 0th layer adopts the pre-built low-resolution face image training set I L , namely I L(0) =I L . When step 4.2 is subsequently executed, the corresponding low-resolution intermediate dictionary I is adopted according to the value of b L(1) , I L(2) ,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a facial image super-resolution method based on dictionary asymptotic updating. In the training stage, super-resolution reconstruction is carried out on low-resolution facial images of a low-resolution facial image training set with a one removing method to obtain a low-resolution intermediate dictionary; the low-resolution intermediate dictionary serves as a new low-resolution facial image training set for inputting, and reconstruction is carried out to obtain a new low-resolution intermediate dictionary; the process is repeated, and finally multiple low-resolution intermediate dictionaries are obtained. In the testing stage, according to the input low-resolution facial images, the prior low-resolution intermediate dictionary and a high-resolution facial image training set, super-resolution reconstruction is carried out on the input low-resolution facial images to obtain pre-estimated high-resolution facial images; the process is repeated, and finally the high-resolution facial images are reconstructed. By means of the facial image super-resolution method, the reconstruction effect which is high in quality and close to a true condition can be achieved.

Description

technical field [0001] The invention relates to the field of image super-resolution, in particular to a face image super-resolution method based on dictionary asymptotic update. Background technique [0002] Face image super-resolution technology refers to using the training library composed of low-resolution face sample images and high-resolution face sample images to learn the relationship between low-resolution images and high-resolution images, and use the learned Relation The process of predicting a high-resolution face image given an input low-resolution face image. It has a wide application background in the fields of intelligent video surveillance, digital entertainment, face synthesis and recognition, etc. [0003] Since the image super-resolution technology was proposed in 1984, it has attracted extensive attention from scholars in the fields of computer vision and machine learning. Freeman et al. (Document 1: W. Freeman, E. Pasztor, and O. Carmichael. Learning l...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/50G06K9/62
Inventor 胡瑞敏江俊君付吉灿韩镇董小慧关健王正
Owner WUHAN UNIV